align-intent
Skill73 starsChanged 10 days agoMITView on GitHub
Use when 使用者要求確認你對當前需求、目標或範圍的理解(「你能理解我的意思嗎」「先對齊理解」「不是這個意思」),或既有機制明確呼叫來處理會影響下一步的理解分歧。適用於提出想法時與對話中途。Do not use for:只是聽不懂說明(wait-what)、查證事實、索取第二意見(advisor)、尚無目標的發散探索(brainstorm)、整套設計訪談(grill-me),或一般任務的固定開場。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- ahmadghoniem/skillstheir own version, first seen Sep 14, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- ahmadghoniem/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository42 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- folder-level/CLAUDE.mdCLAUDE.md
- absorb-packSkill
- agent-authoringSkill
- agent-dispatchSkill
- auto-choiceSkill
- brainstormSkill
- cavemanSkill
- check-my-stackSkill
- debuggingSkill
- domain-modelingSkill
- e2e-contractSkill
- e2e-explore-then-batchSkill
- e2e-routeSkill
- figma-context-budgetSkill
- find-skillsSkill
- gate-authoringSkill
- github-repo-researchSkill
- grill-meSkill
- grill-with-docsSkill
- handoff-implSkill
- implementSkill
- model-onboardSkill
- mutation-testingSkill
- prototypeSkill
- receiving-code-reviewSkill
- research-before-answerSkill
- resolving-merge-conflictsSkill
- review-implementSkill
- review-methodSkill
- review-zhSkill
- skill-creatorSkill
- strategic-compactSkill
- tddSkill
- to-questionnaireSkill
- to-specSkill
- to-ticketsSkill
- wayfinderSkill
- wizardSkill
- workflow-hardeningSkill
- write-pr-descriptionSkill
- zoom-outSkill
The file
Files
對齊理解
把「你能理解我的意思嗎?」變成可檢查的理解,而不是一句「懂了」後自行開工。重述、列假設、沒有發現差異,都不等於使用者已確認或授權。
入口
- 使用者可用
/align-intent或自然語言叫用,不需要參數,也不必先證明哪裡錯。 - 保留模型與既有機制的呼叫能力。機制叫用時先帶齊:原任務、原話或可讀位置、具體分歧、受影響的下一步與返回點。只有「可能沒對齊」不足以啟動;缺少材料就交回呼叫方,不自行補造。
- 這份 skill 不替任何流程新增固定關卡;呼叫方必須明確接線。已在對齊同一件事時沿用當輪,不遞迴叫自己。
做法
- 停在理解層。 暫不啟動新的實作、派工或對外動作;先辨識這次是使用者直接叫用,還是機制交入。既有背景工作若未確認停止,就如實說仍在跑,不把「暫不做新動作」說成全部已停。
- 回讀,再重述。 從當前對話與已給材料找出使用者要的結果、關鍵限制,以及最近的修正。用短句說「我的理解是……」,把使用者原話與自己的推測分開;提及差異時指出對應原話或位置。不要要求重講已有資訊,不為了對齊擴搜個人歷史。原文不可得就標未知,不假裝已核對。
- 只處理影響下一步的缺口。 能從材料修正的就先修正自己的理解;仍有會改變目標、範圍或授權的歧義,才問最關鍵的一題並等答案。不把推測寫成「你已選擇」,也不以「有錯請糾正」取代這次必要的確認。不固定列三項、不硬找常見錯誤、不猜使用者的隱藏動機;未發現差異就寫「目前未發現差異」,不宣稱雙方已對齊。若後續回答揭露另一個承重缺口,再釐清,不為遵守一題而跳過它。
- 交還控制。 簡短回報「目前理解/修正或仍缺的資訊/下一步停或返回」,無內容的欄位省略。
- 使用者直接叫用:回報後停住;只有本次已明確授權對齊後續做,且修正沒有超出該授權時才續做。問「理解嗎」不是執行授權。
- 機制叫用:把修正與未解缺口交回指定位置,由原流程依既有授權繼續或等待,不替呼叫方選顧問、派工、改稿或擴權。
- 修正使舊計畫失效:指出哪個下一步不能照舊,停在那裡等決定;不偷偷換案,也不硬接原計畫。
以「使用者能指出理解哪裡不對、下一步沒有越權」結束,不以模型自評理解充分結束。這是對話指引,不是攔截工具或取消背景工作的機械保證。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

